Dynamically reconfiguring predictive analytics within workflows using selective user feedback

Abstract

Methods and arrangements for managing and enhancing workflow. A work item is accepted and the is routed from a first node to a second node based on a predictive analytics model. The predictive analytics model is validated, and is reconfigured responsive to the validating.

What is claimed is: 
     
       1. A method comprising:
 accepting a work item; 
 routing the work item from a first node to a second node based on a predictive analytics model; 
 validating the predictive analytics model; and 
 reconfiguring the predictive analytics model responsive to said validating. 
 
     
     
       2. The method according to  claim 1 , wherein:
 said validating comprises querying a user to suggest a routing change of the work item; and 
 said reconfiguring comprises reconfiguring the predictive analytics model based on the suggested routing change. 
 
     
     
       3. The method according to  claim 2 , wherein said validating further comprises ascertaining whether a node is a candidate for a routing change. 
     
     
       4. The method according to  claim 3 , wherein said ascertaining whether a node is a candidate comprises reviewing historical statistics of work item routing to nodes. 
     
     
       5. The method according to  claim 3 , wherein said querying comprises querying the user upon ascertaining a candidate node for a routing change. 
     
     
       6. The method according to  claim 5 , wherein said querying comprises guiding the user via providing a narrowed set of choices for candidate nodes for routing changes. 
     
     
       7. The method according to  claim 3 , wherein said reconfiguring comprises choosing the predictive analytics model for reconfiguration based on its association with an ancestor node of two more candidate nodes for routing changes. 
     
     
       8. The method according to  claim 2 , wherein:
 said validating comprises providing a user with random samples of work item routings to nodes; and 
 said querying comprises querying the user to suggest a routing change from among the random samples.